{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:RI3ISAGFEN5N53SNU37WBUI6TN","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"5e0d20ff1a6fe430b37c7095bf5a01545470982a9589bca3cb5493f50549bec4","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-08-10T21:43:58Z","title_canon_sha256":"f71e774d3ed4e6edcf0b5b797b61953d2cc641b6c5bad06f34ee80bad21b5bf5"},"schema_version":"1.0","source":{"id":"2608.10258","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.10258","created_at":"2026-08-12T00:23:12Z"},{"alias_kind":"arxiv_version","alias_value":"2608.10258v1","created_at":"2026-08-12T00:23:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.10258","created_at":"2026-08-12T00:23:12Z"},{"alias_kind":"pith_short_12","alias_value":"RI3ISAGFEN5N","created_at":"2026-08-12T00:23:12Z"},{"alias_kind":"pith_short_16","alias_value":"RI3ISAGFEN5N53SN","created_at":"2026-08-12T00:23:12Z"},{"alias_kind":"pith_short_8","alias_value":"RI3ISAGF","created_at":"2026-08-12T00:23:12Z"}],"graph_snapshots":[{"event_id":"sha256:789d4a7173f3729f3aaee83ded11d8ca6abf07134d4aeac940a73b91ea8b6587","target":"graph","created_at":"2026-08-12T00:23:12Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2608.10258/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) increasingly provide conversational health information that may influence treatment decisions, yet existing benchmarks do not isolate whether medication-safety boundaries persist across follow-ups after explicit self-treatment intent. We introduce TAF-MED, a physician-reviewed benchmark of 500 fixed three-turn scenarios, and evaluate eight LLMs across 4,000 conversations. A rubric-based automated judge labelled responses as SAFE, LEAKY, or UNSAFE, and two physicians independently annotated a model-balanced random subset of 400 conversations. We assessed unsafe guid","authors_text":"Raphael Schmitt, Waleed Jamil","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-08-10T21:43:58Z","title":"TAF-MED: Multi-Turn Safety Refusal Collapse in LLMs Under Declared Self-Treatment Intent"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.10258","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:9f9da78ef936cc05f3009cc2a24b8cc22074ed6f26e372e6b5c195b640ef3413","target":"record","created_at":"2026-08-12T00:23:12Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"5e0d20ff1a6fe430b37c7095bf5a01545470982a9589bca3cb5493f50549bec4","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-08-10T21:43:58Z","title_canon_sha256":"f71e774d3ed4e6edcf0b5b797b61953d2cc641b6c5bad06f34ee80bad21b5bf5"},"schema_version":"1.0","source":{"id":"2608.10258","kind":"arxiv","version":1}},"canonical_sha256":"8a368900c5237adeee4da6ff60d11e9b5355673ee20f0a00925685490c2348fa","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8a368900c5237adeee4da6ff60d11e9b5355673ee20f0a00925685490c2348fa","first_computed_at":"2026-08-12T00:23:12.035960Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-12T00:23:12.035960Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"xVJ4XuwPuT/nS6l4kndlMTQpU3xf9BNVFvZrpKMRT6p7WoFFbkEITUrybLaquF2h/Z9ahIUCeUajyN+4RvoaDQ==","signature_status":"signed_v1","signed_at":"2026-08-12T00:23:12.037395Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.10258","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9f9da78ef936cc05f3009cc2a24b8cc22074ed6f26e372e6b5c195b640ef3413","sha256:789d4a7173f3729f3aaee83ded11d8ca6abf07134d4aeac940a73b91ea8b6587"],"state_sha256":"0a2186d98a8b1c6caca3cb24212b33604bd32b2530d788493bffc5cbc56e10a8"}